AI is powerful, but it is not magic. Just because developers use AI tools does not mean outcomes will improve automatically.

MLCommons today released AILuminate, a new benchmark test for evaluating the safety of large language models. Launched in 2020, MLCommons is an industry consortium backed by several dozen tech firms.

Researchers behind a new study say that the methods used to evaluate AI systems’ capabilities routinely oversell AI performance and lack scientific rigor. The study, led by researchers at the Oxford ...